Claude Opus 4.7 · BrowseComp(1,266 题;单代理与多代理按协议区分),发布表报告值配置,Accuracy 79.3%(具体成绩公布时间未确认)。官方出处 Introducing Claude Opus 4.7(主文,官方发布页;本地保存 HTML/TXT 与主表 PNG:本地留存副本、本地留存副本、本地留存副本;原文发布日期 2026-04-16,当前修订时间未知)BrowseComp 行,https://www.anthropic.com/news/claude-opus-4-7#testing-claude-opus-47。Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-4-7/ev-op47-browse/
关联成绩与条件
Claude Opus 4.7 · BrowseComp 成绩与配置
指标与成绩
配置与评测条件
证据关系
Accuracy79.3%原文 79.3% · 单位 %
公布 未确认
发布表报告值
设置
System Card §8.1 standard configuration: adaptive thinking at max effort; default temperature/top_p; averaged over 5 trials. Context sizes are evaluation-dependent and do not exceed 1M tokens; retain all section-specific exceptions on their results.
未知项
Per-benchmark tools, context/token cap, resolution, trial count, harness and other exceptions are recorded on each result when stated.
工具
允许工具
推理预算
max
框架
未记录
协议
BrowseComp; web search, web fetch, programmatic tool calling and code execution.
条件
Thinking disabled; max effort; 10M total-token limit; context compaction triggered at 200K.
Claude Opus 4.7 · BrowseComp (1,266 题;单代理与多代理按协议区分) 79.3% · Main text evidence (ev-op47-browse)
Official source for BrowseComp · 1,266 题;单代理与多代理按协议区分 in Claude Opus 4.7. 发布表报告值 · 79.3%. See “Introducing Claude Opus 4.7” at BrowseComp 行. Evidence ev-op47-browse.
Claude Opus 4.7 · BrowseComp (1,266 题;单代理与多代理按协议区分), configuration 发布表报告值, Accuracy 79.3% (exact score publication date unconfirmed). See “Introducing Claude Opus 4.7” at BrowseComp 行. View score conditions
Unconfirmed · Launch or later disclosure unconfirmed
Collected
Historical basis
No reliable historical version evidence available
Citation text
Claude Opus 4.7 · BrowseComp (1,266 题;单代理与多代理按协议区分), configuration 发布表报告值, Accuracy 79.3% (exact score publication date unconfirmed). Official source: Introducing Claude Opus 4.7 (Main text, 官方发布页;本地保存 HTML/TXT 与主表 PNG:本地留存副本、本地留存副本、本地留存副本;原文发布日期 2026-04-16,当前修订时间未知), BrowseComp 行, https://www.anthropic.com/news/claude-opus-4-7#testing-claude-opus-47. Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-4-7/ev-op47-browse/?lang=en
Related scores and conditions
Claude Opus 4.7 · BrowseComp scores and configurations
Metric and score
Configuration and evaluation conditions
Evidence relation
Accuracy79.3%Reported 79.3% · Unit %
Published Unconfirmed
发布表报告值
Settings
System Card §8.1 standard configuration: adaptive thinking at max effort; default temperature/top_p; averaged over 5 trials. Context sizes are evaluation-dependent and do not exceed 1M tokens; retain all section-specific exceptions on their results.
Unknowns
Per-benchmark tools, context/token cap, resolution, trial count, harness and other exceptions are recorded on each result when stated.
Tools
Tools allowed
Reasoning budget
max
Framework
not recorded
Protocol
BrowseComp; web search, web fetch, programmatic tool calling and code execution.
Conditions
Thinking disabled; max effort; 10M total-token limit; context compaction triggered at 200K.